A Hindi-language screen-recorded tutorial (170K followers) showed the AI’s 'Today' panel with tasks like 'Build Jeep demo video' and 'Create EX demo video.' The speaker pasted an Instagram link into chat and the AI produced a detailed production plan for a Jeep restoration video — rust removal, sanding, olive-green airbrush, chrome detailing, turntable reveal — plus optimal posting time (7-9 PM IST), title length guidance, and hashtags like #RustyJeep.
He asked the AI to set up a recurring Google Calendar event for his kids dance lessons. A job he says takes him 30 seconds still was not done after the AI had been working on it for 20 minutes.
This one went wrong. See what happened before you try it.
After reading the AI’s summary of an embargoed PR pitch, Ulanoff had it draft a reply. The first draft overpromised a meeting, so he had it strip the meeting references to just agreeing to the embargo and getting images and details.
He asked the AI to make a marketing video for his app, Astro Editor. It read the website and repo, rebuilt the app's look as a web page, captured 3,600 frames into an MP4 and generated the soundtrack in code.
He had a rough script that launched internet radio stations on his Linux desktop. The AI made it safe and finished: it checks the saved player, searches the Radio Browser database, adds tests, a manual and a README, and pushed it to GitHub.
He set up the AI with five helpers for his YouTube work. One scouts what is new every Monday, one helps write scripts, one makes all his thumbnails, one updates his personal brand GitHub repo, and one helps him engage on X.
Ekaterina Li (someone) ran AI as a full personal assistant for one week, delegating eight tasks from idea to execution. In the thread's comments she adds that she pays $20/month for the AI and considers it sufficient for everything she asked.
He used the AI API to draft his articles automatically for a week. Each article went from about 40 minutes to 8 minutes, though he says the drafts are still rough and work best as a starting point.
This only partly worked. Worth knowing before you try it.
Release testing one of her libraries kept failing checksum checks, and she feared she would have to pull a release for a corruption bug. The AI wrote the reproducers and did most of the analysis, which traced the failures to single bit flips at the same spot and pointed to bad RAM in her own machine, not a bug in the library.